Oxford Pet Segmentation

--- library_name: segmentation-models-pytorch license: mit pipeline_tag: image-segmentation tags: - model_hub_mixin - pytorch_model_hub_mixin - segmentation-models-pytorch - semantic-segmentation - pytorch languages: - python --- # FPN Model Card Table of Contents: - [Load trained model](#load-trained-model) - [Model init parameters](#model-init-parameters) - [Model metrics](#model-metrics) - [Dataset](#dataset) ## Load trained model ```python import segmentation_models_pytorch as smp model = smp.from_pretrained("<save-directory-or-this-repo>") ``` ## Model init parameters ```python model_init_params = { "encoder_name": "resnet34", "encoder_depth": 5, "encoder_weights": "imagenet", "decoder_pyramid_channels": 256, "decoder_segmentation_channels": 128, "decoder_merge_policy": "add", "decoder_dropout": 0.2, "decoder_interpolation": "nearest", "in_channels": 3, "classes": 1, "activation": None, "upsampling": 4, "aux_params": None } ``` ## Model metrics ```json [ { "test_per_image_iou": 0.9084645509719849, "test_dataset_iou": 0.9154928922653198 } ] ``` ## Dataset Dataset name: Oxford Pet ## More Information - Library: https://github.com/qubvel/segmentation_models.pytorch - Docs: https://smp.readthedocs.io/en/latest/ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin)